Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 394 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2791. Min Act: -0.0001

Data Index: 1233978 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2711. Min Act: -0.0001

Data Index: 1120770 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2542. Min Act: -0.0001

Data Index: 1031332 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2581. Min Act: -0.0001

Data Index: 1205379 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2375. Min Act: -0.0001

Data Index: 613498 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2516. Min Act: -0.0001

Data Index: 673925 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2361. Min Act: -0.0001

Data Index: 720050 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2327. Min Act: -0.0001

Data Index: 520821 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2408. Min Act: -0.0001

Data Index: 921778 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2313. Min Act: -0.0001

Data Index: 196187 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2285. Min Act: -0.0001

Data Index: 1311427 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2426. Min Act: -0.0001

Data Index: 689508 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2258. Min Act: -0.0001

Data Index: 347100 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2308. Min Act: -0.0001

Data Index: 960582 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2305. Min Act: -0.0001

Data Index: 1096907 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2347. Min Act: -0.0001

Data Index: 959057 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2096. Min Act: -0.0000

Data Index: 385441 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2020. Min Act: -0.0001

Data Index: 258431 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2154. Min Act: -0.0001

Data Index: 553997 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2148. Min Act: -0.0001

Data Index: 480123 (C4 (Web Text))

Max Activating Token Index: 462